[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-602250-105":59,"doc-detail-602250-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","multimodal-data-fusion-to-detect-preknowledge-test-taking-behavior-using-machine-learning","Multimodal Data Fusion to Detect Preknowledge Test-Taking Behavior Using Machine Learning","","High-stakes assessment decisions in admissions, medical certifications, and military recruitment depend on scores from large-scale testing, making reliable inference about test-takers essential. Aberrant practices, such as prior practice of real items, can undermine validity and fairness, so post-collection detection strategies are needed. This study applies machine learning with multimodal data fusion that integrates eye-tracking bio-information and psychometric indicators, including response times and item responses, for identifying aberrant behavior in technology-assisted remote testing settings.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/multimodal-data-fusion-to-detect-preknowledge-test-taking-behavior-using-machine-learning/602250/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/multimodal-data-fusion-to-detect-preknowledge-test-taking-behavior-using-machine-learning/602250.png","ImageObject",300,407,{"name":92,"@type":93},"dawugda","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is detecting aberrant test-taking behavior important in remote assessments?","Question",{"text":112,"@type":113},"High-stakes decisions rely on test scores to support valid inferences about performance. Aberrant practices like prior item exposure can compromise reliability and fairness, especially in settings that are harder to supervise.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What multimodal data does the study integrate to detect aberrant behavior?",{"text":117,"@type":113},"It combines bio-information technology signals such as eye-tracking with psychometric measures including response times and item responses, using multimodal data fusion within machine learning methods.",{"name":119,"@type":110,"acceptedAnswer":120},"How do traditional approaches detect suspicious responses in online exams?",{"text":121,"@type":113},"Researchers use person-fit statistics based on item responses and indices derived from response times (e.g., RT residual-based methods) to measure deviations from expectations given an examinee’s ability or working efficiency.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},602250,1792432089,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},3985747870947,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","Multimodal Data Fusion to Detect Preknowledge Test-Taking Behavior Using Machine Learning  \nKaiwen Man 1  \nEducational and Psychological Measurement  \n2024, Vol. 84(4) 753–779  \n􀀂 The Author(s) 2023 Article reuse guidelines:  \n[sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/00131644231193625](DOI: 10.1177/00131644231193625)[ ](DOI: 10.1177/00131644231193625)[journals.sagepub.com/home/epm](journals.sagepub.com/home/epm)  \nAbstract  \nIn various fields, including college admission, medical board certifications, and military recruitment, high-stakes decisions are frequently made based on scores obtained from large-scale assessments. These decisions necessitate precise and reliable scores that enable valid inferences to be drawn about test-takers. However, the ability of such tests to provide reliable, accurate inference on a test-taker’s performance could be jeopardized by aberrant test-taking practices, for instance, practicing real items prior to the test. As a result, it is crucial for administrators of such assessments to develop strategies that detect potential aberrant test-takers after data collection. The aim of this study is to explore the implementation of machine learning methods in combination with multimodal data fusion strategies that integrate bio-information technology, such as eye-tracking, and psychometric measures, including response times and item responses, to detect aberrant test-taking behaviors in technologyassisted remote testing settings.  \nKeywords  \ntechnology enhanced assessment, cheating detection, multimodal data fusion, item response theory, response times, eye-tracking  \nThe demand for ongoing tool improvement to examine test-taker behavior is driven by the increasing public popularity of remote online-based assessment and testing. For instance, several at-home testing programs were started during the COVID-19  \n1 The University of Alabama, Tuscaloosa, USA  \nCorresponding Author:  \nKaiwen Man, Educational Research Program, Educational Studies in Psychology, Research Methodology, and Counseling, The University of Alabama, 313 Carmichael, Box 870231, Tuscaloosa, AL 35487, USA. Email: [kman@ua.edu](kman@ua.edu)  \nepidemic, providing test-takers with a convenient and safe alternative to taking their tests at a testing facility. Making sure test-takers actively and accurately answer questions without cheating is a crucial and urgent subject that must be addressed in such distant and challenging-to-supervise test-taking environments. To address these concerns, testing companies presently use the technology-assisted online proctoring system to oversee test-taker behavior and performance, aiming to decrease the occurrence of cheating.  \nIn such a technology-assisted remote or home-based testing environment, multimodal feedback data can be gathered to track test-takers’ performing process in a formative manner via various technical equipments (e.g., online-based eye-tracking camera, motion tracker). The collected data could be used to (1) directly reflect learners’ cognitive outcomes or performance accuracy while working on a task; (2) facilitate the inferences regarding learners’ activities while performing a task, such as response times (RTs) and action sequences (ASs); and (3) demonstrate learners’ biological reactions to the stimulus while reacting on a task’s stimulus such as eye-movements and pupil reactions (Agard & von Davier, 2018; Toton & Maynes, 2019).  \nTo ensure integrity and fairness during online exams, researchers have proposed various solutions, including person-fit statistics and indices based on item responsesand RTs. Person-fit statistics, such as Guttman error (Guttman, 1944), Lz index (Drasgow et al., 1985), and Ht index (Sijtsma & Meijer, 1992), measure the extent to which an individual’s responses deviate from what is expected based on their ability level. Representative indices based on item RTs, such as RT resid","cbCaipryzyyN7UIZ","https://ap.wps.com/l/cbCaipryzyyN7UIZ","pdf",2558166,27,"English","# Abstract\n# Background and motivation\n## High-stakes assessment validity\n## Remote testing and proctoring\n# Multimodal data and feedback signals\n## Cognitive and performance indicators\n## Biological reactions\n# Existing integrity methods\n## Person-fit statistics\n## Response-time based indices\n# Data-mining approaches for cheating detection\n## Supervised vs. unsupervised learning\n# Machine-learning with multimodal fusion (study focus)","[{\"question\":\"Why is detecting aberrant test-taking behavior important in remote assessments?\",\"answer\":\"High-stakes decisions rely on test scores to support valid inferences about performance. Aberrant practices like prior item exposure can compromise reliability and fairness, especially in settings that are harder to supervise.\"},{\"question\":\"What multimodal data does the study integrate to detect aberrant behavior?\",\"answer\":\"It combines bio-information technology signals such as eye-tracking with psychometric measures including response times and item responses, using multimodal data fusion within machine learning methods.\"},{\"question\":\"How do traditional approaches detect suspicious responses in online exams?\",\"answer\":\"Researchers use person-fit statistics based on item responses and indices derived from response times (e.g., RT residual-based methods) to measure deviations from expectations given an examinee’s ability or working efficiency.\"}]","Multimodal Data Fusion to Detect Preknowledge Test-Taking Behavior Using Machine Learning | PDF",1792094336,68]